AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

MambaVoiceCloning: Efficient and Expressive Text-to-Speech via State-Space Modeling and Diffusion Control

Sahil Kumar, Namrataben Patel, Honggang Wang, Youshan Zhang

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: Neural text-to-speech synthesis · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add AdaLN style modulation to gated fusion (ablation)MVC text encoder · LJSpeech long-formMOS-long: 4.02 -> 4.16Improved
add gating to AdaLN-only fusion (ablation)MVC text encoder · LJSpeech long-formMOS-long: 3.95 -> 4.16Improved
add gating and AdaLN to concat fusion (ablation)MVC text encoder · LJSpeech long-formpitch RMSE (Hz): 2.89 -> 1.92Improved
add gating and AdaLN to concat fusion (ablation)MVC text encoder · LJSpeech long-formMOS-long: 3.64 -> 4.16Improved
add Expressive Mamba predictor (ablation)MVC · OOD setCMOS-N: -0.41 drop when removedImproved
add Bi-Mamba text encoder (ablation)MVC · OOD setCMOS-N: -0.38 drop when removedImproved
add Temporal Bi-Mamba encoder (ablation)MVC · OOD setCMOS-N: -0.36 drop when removedImproved
replace BiLSTM text encoder with 6 Mamba layers (ablation)MVC text encoder · LJSpeechMOS ID: 3.61 -> 3.87Improved
increase Mamba text encoder depth from 6 to 7 layers (ablation)MVC text encoder · LJSpeechMOS ID: 3.87 -> 3.90No clear effect
increase Mamba text encoder depth from 2 to 6 layers (ablation)MVC text encoder · LJSpeechpitch RMSE (Hz): 27.5 -> 23.2Improved
increase diffusion steps from 5 to 9 (ablation)MVC · LJSpeech validationMOS-N: 3.87 -> 3.89 (RTF 0.0177 -> 0.0221)No clear effect
increase diffusion steps from 3 to 5 (ablation)MVC · LJSpeech validationMOS-N: 3.62 -> 3.87Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy